Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3685 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0524. Min Range: -1.0524

Max Act: 1.0524. Min Act: -0.0000

Data Index: 287086 (The Pile)

Max Activating Token Index: 874

Text #1

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.7932. Min Act: -0.0000

Data Index: 96654 (The Pile)

Max Activating Token Index: 122

Text #2

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.8267. Min Act: -0.0000

Data Index: 340118 (The Pile)

Max Activating Token Index: 994

Text #3

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.7887. Min Act: -0.0000

Data Index: 1673376 (The Pile)

Max Activating Token Index: 597

Text #4

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.8623. Min Act: -0.0000

Data Index: 151092 (The Pile)

Max Activating Token Index: 281

Text #5

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.7907. Min Act: -0.0000

Data Index: 162562 (The Pile)

Max Activating Token Index: 988

Text #6

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.7747. Min Act: -0.0000

Data Index: 705260 (The Pile)

Max Activating Token Index: 352

Text #7

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.7722. Min Act: -0.0000

Data Index: 1962300 (The Pile)

Max Activating Token Index: 637

Text #8

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.8038. Min Act: -0.0000

Data Index: 161706 (The Pile)

Max Activating Token Index: 584

Text #9

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.7591. Min Act: -0.0000

Data Index: 339258 (The Pile)

Max Activating Token Index: 422

Text #10

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.7286. Min Act: -0.0000

Data Index: 896162 (The Pile)

Max Activating Token Index: 802

Text #11

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.8178. Min Act: -0.0000

Data Index: 1805805 (The Pile)

Max Activating Token Index: 553

Text #12

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.7253. Min Act: -0.0000

Data Index: 1244054 (The Pile)

Max Activating Token Index: 314

Text #13

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.7096. Min Act: -0.0000

Data Index: 1578850 (The Pile)

Max Activating Token Index: 641

Text #14

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.7743. Min Act: -0.0000

Data Index: 1812130 (The Pile)

Max Activating Token Index: 847

Text #15

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.7134. Min Act: -0.0000

Data Index: 1239361 (The Pile)

Max Activating Token Index: 222

Text #16

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.7566. Min Act: -0.0000

Data Index: 65350 (The Pile)

Max Activating Token Index: 780

Text #17

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.6558. Min Act: -0.0001

Data Index: 67173 (The Pile)

Max Activating Token Index: 372

Text #18

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.7170. Min Act: -0.0000

Data Index: 1651483 (The Pile)

Max Activating Token Index: 244

Text #19

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.5886. Min Act: -0.0000

Data Index: 1881715 (The Pile)

Max Activating Token Index: 200